GenAttack: practical black-box attacks with gradient-free optimization

Pages: 1111 - 1119
Published: Jul 13, 2019
Abstract
Deep neural networks are vulnerable to adversarial examples, even in the black-box setting, where the attacker is restricted solely to query access. Existing black-box approaches to generating adversarial examples typically require a significant number of queries, either for training a substitute network or performing gradient estimation. We introduce GenAttack, a gradient-free optimization technique that uses genetic algorithms for synthesizing...
Paper Fields
Paper Details
Title
GenAttack: practical black-box attacks with gradient-free optimization
Published Date
Jul 13, 2019
Journal
Pages
1111 - 1119
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.